Description

You will own the implementation and optimization of scalable ML systems, covering the full lifecycle from evaluation to deployment.

This role is on-site.

Responsibilities

• Design and implement end-to-end ML pipelines, including metric generation and model monitoring.
• Optimize ML models through quantization, pruning, speculative decoding, and system-level bottleneck resolution.
• Manage Java library dependencies, package distribution, and algorithm implementation.
• Lead inter-team communication, define technical problems, and maintain crisp documentation.
• Ensure deadlines are met while collaborating effectively with team members.

Required Skills

• 5+ years of experience in ML Ops or related engineering roles.
• Hands-on proficiency with Python, TensorFlow, and PyTorch within the last 12 months.
• Experience with Java for library management and distribution.
• Strong knowledge of CI/CD pipelines, Terraform, Docker, and Kubernetes.
• Proven ability to abstract technical details and communicate clearly.
• Experience with prompt engineering and statistical modeling.
• Ability to identify system bottlenecks and resolve them from a systems perspective.

Preferred Skills

• Experience with GCP ML tech stack and Infrastructure as Code (IaC).
• Familiarity with big data technologies such as Apache Spark or Hadoop.
• Experience with on-device ML system development.

Key Skills

Education

Any Gradute